AI Rate CardClaude Haiku 4.5 (latest) vs GPT-5 Nano: API price and specs
GPT-5 Nano is 95% cheaper than Claude Haiku 4.5 (latest) on input price.
GPT-5 Nano is 92% cheaper than Claude Haiku 4.5 (latest) on output price.
GPT-5 Nano is 94% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.
GPT-5 Nano has a 100% larger context than Claude Haiku 4.5 (latest).
| Field | Claude Haiku 4.5 (latest) | GPT-5 Nano |
|---|---|---|
| Lowest input, per 1M | $0.50 +1900% | $0.025 |
| Median input, per 1M | $1.00 +1900% | $0.05 |
| Lowest output, per 1M | $2.50 +1150% | $0.20 |
| Median output, per 1M | $5.00 +1150% | $0.40 |
| Lowest unit price | $0.001 / request | — |
| Cost of 1M in + 200k out | $1.00 +1438.5% | $0.065 |
| Context | 200K +50% | 400K |
| Max output | 64K +50% | 128K |
| Providers | 34 | 25 +26.5% |
| Regions | APAC, AU, EU, GLOBAL, IN, JP, US | EU, GLOBAL, US |
| Accepts | application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text | file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | openrouter | openrouter |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
abacus, aihubmix, aiml, azure, cometapi, cortecs, digitalocean, edenai, fastrouter, helicone, impossibl, jiekou, kilo, meganova, nearai, ofox, opencode, openrouter, orcarouter, poe, requesty, trustedrouter, vercel, zenmux
Frequently asked questions
Which is cheaper, Claude Haiku 4.5 (latest) or GPT-5 Nano?
GPT-5 Nano is 95% cheaper than Claude Haiku 4.5 (latest) on input price. GPT-5 Nano is 92% cheaper than Claude Haiku 4.5 (latest) on output price. GPT-5 Nano is 94% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.
Which has the larger context, Claude Haiku 4.5 (latest) or GPT-5 Nano?
Claude Haiku 4.5 (latest): 200K tokens; GPT-5 Nano: 400K tokens.
Where can I use both Claude Haiku 4.5 (latest) and GPT-5 Nano?
abacus, aihubmix, aiml, azure, cometapi, cortecs, digitalocean, edenai, fastrouter, helicone, impossibl, jiekou, kilo, meganova, nearai, ofox, opencode, openrouter, orcarouter, poe, requesty, trustedrouter, vercel, zenmux